{"id":"https://openalex.org/W2963765325","doi":"https://doi.org/10.3390/info10080247","title":"Crowdsourcing the Paldaruo Speech Corpus of Welsh for Speech Technology","display_name":"Crowdsourcing the Paldaruo Speech Corpus of Welsh for Speech Technology","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2963765325","doi":"https://doi.org/10.3390/info10080247","mag":"2963765325"},"language":"en","primary_location":{"id":"doi:10.3390/info10080247","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info10080247","pdf_url":"https://www.mdpi.com/2078-2489/10/8/247/pdf","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/10/8/247/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038532459","display_name":"Sarah Cooper","orcid":"https://orcid.org/0000-0002-2105-8338"},"institutions":[{"id":"https://openalex.org/I161548249","display_name":"Bangor University","ror":"https://ror.org/006jb1a24","country_code":"GB","type":"education","lineage":["https://openalex.org/I161548249"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Sarah Cooper","raw_affiliation_strings":["School of Languages, Literatures and Linguistics, Bangor University, Bangor, Gwynedd LL57 2DG, UK"],"raw_orcid":"https://orcid.org/0000-0002-2105-8338","affiliations":[{"raw_affiliation_string":"School of Languages, Literatures and Linguistics, Bangor University, Bangor, Gwynedd LL57 2DG, UK","institution_ids":["https://openalex.org/I161548249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103109479","display_name":"Dewi Jones","orcid":"https://orcid.org/0000-0003-1263-6332"},"institutions":[{"id":"https://openalex.org/I161548249","display_name":"Bangor University","ror":"https://ror.org/006jb1a24","country_code":"GB","type":"education","lineage":["https://openalex.org/I161548249"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dewi Bryn Jones","raw_affiliation_strings":["Language Technologies Unit, Bangor University, Bangor, Gwynedd LL57 2DG, UK"],"raw_orcid":"https://orcid.org/0000-0003-1263-6332","affiliations":[{"raw_affiliation_string":"Language Technologies Unit, Bangor University, Bangor, Gwynedd LL57 2DG, UK","institution_ids":["https://openalex.org/I161548249"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043532611","display_name":"Delyth Prys","orcid":"https://orcid.org/0000-0002-4909-6926"},"institutions":[{"id":"https://openalex.org/I161548249","display_name":"Bangor University","ror":"https://ror.org/006jb1a24","country_code":"GB","type":"education","lineage":["https://openalex.org/I161548249"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Delyth Prys","raw_affiliation_strings":["Language Technologies Unit, Bangor University, Bangor, Gwynedd LL57 2DG, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Unit, Bangor University, Bangor, Gwynedd LL57 2DG, UK","institution_ids":["https://openalex.org/I161548249"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038532459"],"corresponding_institution_ids":["https://openalex.org/I161548249"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.3877,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81954628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"10","issue":"8","first_page":"247","last_page":"247"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13155","display_name":"Digital Communication and Language","score":0.953499972820282,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13155","display_name":"Digital Communication and Language","score":0.953499972820282,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10383","display_name":"Language, Discourse, Communication Strategies","score":0.9412000179290771,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11640","display_name":"Linguistic Variation and Morphology","score":0.9384999871253967,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.8452179431915283},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8082153797149658},{"id":"https://openalex.org/keywords/welsh","display_name":"Welsh","score":0.7486572861671448},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.6667324304580688},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5234089493751526},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5142728686332703},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4965510964393616},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.490294486284256},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.468340128660202},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.44222575426101685},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3993510603904724},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34958067536354065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33923545479774475},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3236253559589386},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2487511932849884}],"concepts":[{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.8452179431915283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8082153797149658},{"id":"https://openalex.org/C2780769345","wikidata":"https://www.wikidata.org/wiki/Q9309","display_name":"Welsh","level":2,"score":0.7486572861671448},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.6667324304580688},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5234089493751526},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5142728686332703},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4965510964393616},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.490294486284256},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.468340128660202},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.44222575426101685},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3993510603904724},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34958067536354065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33923545479774475},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3236253559589386},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2487511932849884},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/info10080247","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info10080247","pdf_url":"https://www.mdpi.com/2078-2489/10/8/247/pdf","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9cf6ca203bc7444f9d6fd1f1d7135d42","is_oa":true,"landing_page_url":"https://doaj.org/article/9cf6ca203bc7444f9d6fd1f1d7135d42","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 10, Iss 8, p 247 (2019)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2078-2489/10/8/247/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/info10080247","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information","raw_type":"Text"},{"id":"pmh:oai:research.bangor.ac.uk:publications/f9c5f55e-bed1-4cea-a108-3e0d22c89876","is_oa":true,"landing_page_url":"https://research.bangor.ac.uk/portal/en/researchoutputs/crowdsourcing-the-paldaruo-speech-corpus-of-welsh-for-speech-technology(f9c5f55e-bed1-4cea-a108-3e0d22c89876).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402103","display_name":"Bangor University Research Portal (Bangor University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I161548249","host_organization_name":"Bangor University","host_organization_lineage":["https://openalex.org/I161548249"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Cooper , S , Jones , D B &amp; Prys , D 2019 , ' Crowdsourcing the Paldaruo Speech Corpus of Welsh for Speech Technology ' , Information , vol. 10 , no. 8 , pp. 247 . https://doi.org/10.3390/info10080247","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/info10080247","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info10080247","pdf_url":"https://www.mdpi.com/2078-2489/10/8/247/pdf","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316111","display_name":"Llywodraeth Cymru","ror":"https://ror.org/000wh6t45"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963765325.pdf","grobid_xml":"https://content.openalex.org/works/W2963765325.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W134185222","https://openalex.org/W1485437541","https://openalex.org/W1524333225","https://openalex.org/W1556470778","https://openalex.org/W1585829653","https://openalex.org/W1915463356","https://openalex.org/W2019340066","https://openalex.org/W2019645080","https://openalex.org/W2091746061","https://openalex.org/W2093658447","https://openalex.org/W2171913066","https://openalex.org/W2251404002","https://openalex.org/W2299662909","https://openalex.org/W2343295269","https://openalex.org/W2610882818","https://openalex.org/W2620279613","https://openalex.org/W2653413789","https://openalex.org/W2806868415","https://openalex.org/W2894647470","https://openalex.org/W3208832029","https://openalex.org/W4230964063","https://openalex.org/W4241595375","https://openalex.org/W4243756587","https://openalex.org/W6629223880","https://openalex.org/W6631362777","https://openalex.org/W6633249632","https://openalex.org/W6740079130"],"related_works":["https://openalex.org/W2500421879","https://openalex.org/W116652514","https://openalex.org/W2772686614","https://openalex.org/W2186688931","https://openalex.org/W4200068392","https://openalex.org/W2184371793","https://openalex.org/W2537969829","https://openalex.org/W3081800019","https://openalex.org/W4312742405","https://openalex.org/W2014684632"],"abstract_inverted_index":{"Collecting":[0],"speech":[1,31,112],"data":[2,43],"for":[3,29,33,96,108,114,137],"a":[4,122],"low-resource":[5,139],"language":[6],"is":[7],"challenging":[8],"when":[9],"funding":[10],"and":[11,23,49,68,99,102,116,135],"resources":[12],"are":[13,141],"limited.":[14],"This":[15],"paper":[16,37],"describes":[17],"the":[18,25,40,61,74,84,87,93,97,109],"process":[19],"of":[20,42,63,86,111,124],"designing,":[21],"creating":[22],"using":[24,44],"Paldaruo":[26,88],"Speech":[27],"Corpus":[28],"developing":[30],"technology":[32],"Welsh.":[34],"Specifically,":[35],"this":[36],"focuses":[38],"on":[39,47,83],"crowdsourcing":[41],"an":[45],"app":[46],"smartphones":[48],"mobile":[50],"devices,":[51],"allowing":[52],"speakers":[53],"from":[54,77],"across":[55],"Wales":[56],"to":[57,120,132],"contribute.":[58],"We":[59,79],"discuss":[60],"development":[62,110],"reading":[64],"prompts:":[65],"isolated":[66],"words":[67],"full":[69],"sentences,":[70],"as":[71,73,90,92],"well":[72,91],"metadata":[75],"collected":[76],"contributors.":[78],"also":[80],"provide":[81],"background":[82],"design":[85],"App":[89],"main":[94],"uses":[95],"corpus":[98,105],"its":[100],"availability":[101],"licensing.":[103],"The":[104],"was":[106],"designed":[107],"recognition":[113],"Welsh":[115],"has":[117],"been":[118],"used":[119],"create":[121],"number":[123],"other":[125,133,138],"resources.":[126],"These":[127],"methods":[128],"can":[129],"be":[130],"extended":[131],"languages,":[134],"suggestions":[136],"languages":[140],"discussed.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}
